© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 180324
    Prev
    Next
    INDEX
    Explanations

    institutional accreditation or benefits

    np_acts-logits-general · gemini-2.5-flash-lite

    explanation for something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     čini
    0.51
     extremos
    0.50
     ℝ
    0.50
     yattha
    0.49
    benzoimidazole
    0.49
     vattati
    0.48
    企業の
    0.48
    ަނ
    0.47
     desple
    0.47
    amounts
    0.47
    POSITIVE LOGITS
    0.62
     Institution
    0.52
     Hospital
    0.50
     Utility
    0.48
    u
    0.48
     unidentified
    0.48
     Advocate
    0.47
    จาก
    0.46
     Wetland
    0.46
     Injury
    0.46
    Activations Density 0.001%

    No Known Activations